| From 283ee1482f349d6c0c09dfb725db5880afc56813 Mon Sep 17 00:00:00 2001 |
| From: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> |
| Date: Thu, 12 Mar 2015 16:26:00 -0700 |
| Subject: nilfs2: fix deadlock of segment constructor during recovery |
| |
| From: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> |
| |
| commit 283ee1482f349d6c0c09dfb725db5880afc56813 upstream. |
| |
| According to a report from Yuxuan Shui, nilfs2 in kernel 3.19 got stuck |
| during recovery at mount time. The code path that caused the deadlock was |
| as follows: |
| |
| nilfs_fill_super() |
| load_nilfs() |
| nilfs_salvage_orphan_logs() |
| * Do roll-forwarding, attach segment constructor for recovery, |
| and kick it. |
| |
| nilfs_segctor_thread() |
| nilfs_segctor_thread_construct() |
| * A lock is held with nilfs_transaction_lock() |
| nilfs_segctor_do_construct() |
| nilfs_segctor_drop_written_files() |
| iput() |
| iput_final() |
| write_inode_now() |
| writeback_single_inode() |
| __writeback_single_inode() |
| do_writepages() |
| nilfs_writepage() |
| nilfs_construct_dsync_segment() |
| nilfs_transaction_lock() --> deadlock |
| |
| This can happen if commit 7ef3ff2fea8b ("nilfs2: fix deadlock of segment |
| constructor over I_SYNC flag") is applied and roll-forward recovery was |
| performed at mount time. The roll-forward recovery can happen if datasync |
| write is done and the file system crashes immediately after that. For |
| instance, we can reproduce the issue with the following steps: |
| |
| < nilfs2 is mounted on /nilfs (device: /dev/sdb1) > |
| # dd if=/dev/zero of=/nilfs/test bs=4k count=1 && sync |
| # dd if=/dev/zero of=/nilfs/test conv=notrunc oflag=dsync bs=4k |
| count=1 && reboot -nfh |
| < the system will immediately reboot > |
| # mount -t nilfs2 /dev/sdb1 /nilfs |
| |
| The deadlock occurs because iput() can run segment constructor through |
| writeback_single_inode() if MS_ACTIVE flag is not set on sb->s_flags. The |
| above commit changed segment constructor so that it calls iput() |
| asynchronously for inodes with i_nlink == 0, but that change was |
| imperfect. |
| |
| This fixes the another deadlock by deferring iput() in segment constructor |
| even for the case that mount is not finished, that is, for the case that |
| MS_ACTIVE flag is not set. |
| |
| Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> |
| Reported-by: Yuxuan Shui <yshuiv7@gmail.com> |
| Tested-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> |
| Cc: Al Viro <viro@zeniv.linux.org.uk> |
| Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
| Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
| Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
| |
| --- |
| fs/nilfs2/segment.c | 7 ++++--- |
| 1 file changed, 4 insertions(+), 3 deletions(-) |
| |
| --- a/fs/nilfs2/segment.c |
| +++ b/fs/nilfs2/segment.c |
| @@ -1906,6 +1906,7 @@ static void nilfs_segctor_drop_written_f |
| struct the_nilfs *nilfs) |
| { |
| struct nilfs_inode_info *ii, *n; |
| + int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE); |
| int defer_iput = false; |
| |
| spin_lock(&nilfs->ns_inode_lock); |
| @@ -1918,10 +1919,10 @@ static void nilfs_segctor_drop_written_f |
| brelse(ii->i_bh); |
| ii->i_bh = NULL; |
| list_del_init(&ii->i_dirty); |
| - if (!ii->vfs_inode.i_nlink) { |
| + if (!ii->vfs_inode.i_nlink || during_mount) { |
| /* |
| - * Defer calling iput() to avoid a deadlock |
| - * over I_SYNC flag for inodes with i_nlink == 0 |
| + * Defer calling iput() to avoid deadlocks if |
| + * i_nlink == 0 or mount is not yet finished. |
| */ |
| list_add_tail(&ii->i_dirty, &sci->sc_iput_queue); |
| defer_iput = true; |
